BᴀɴɢʟᴀBᴏᴏᴋ: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews

This repository contains the code, data, and models of the paper titled "BᴀɴɢʟᴀBᴏᴏᴋ: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews" published in the Findings of the Association for Computational Linguistics: ACL 2023.

License: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International

Data Format

Each row consists of a book review sample. The table below describes what each column signifies.

Column Title	Description
id	The unique identification number of the sample
Book_Name	The title of the book that has been evaluated by the review
Writer_Name	The name of the book's author
Category	The genre to which the book belongs
Rating	A numerical value $r$ such that $1\leq r \leq 5$ A score reflecting the reviewer's subjective assessment of the book's quality
Review	The review text written by the reviewer
Site	The name of the online bookshop
sentiment	The conveyed sentiment and class label of the review For a review sample $i$ with rating $r_i$, the sentiment label $S_i$ is, $S_i =\begin{cases}Negative, & \text{if $r_i \leq 2$}\\Neutral, & \text{if $r_i = 3$}\\Positive, & \text{if $r_i \geq 4$}\end{cases}$
label	The numerical representation of the sentiment label For a review sample $i$ with sentiment label $S_i$, the numerical label is, $label_i =\begin{cases}0, & \text{if $S_i = Negative$}\\1, & \text{if $S_i = Neutral$}\\2, & \text{if $S_i = Positive$}\end{cases}$

Data Construction

Data Collection Process

For the data collection and preparation process of the BᴀɴɢʟᴀBᴏᴏᴋ dataset, we first compile a list of URLs for authors from online bookstores. From there, we procure URLs for the books. We meticulously scrape information such as book titles, author names, book categories, review texts, reviewer names, review dates, and ratings by utilizing these book URLs.

Labeling, Translation, and Validation of the Curated Samples

If a review does not have a rating, we deem it unannotated. Reviews with a rating of 1 or 2 are classified as negative, a rating of 3 is considered neutral, and a rating of 4 or 5 is classified as positive. After discarding the unannotated reviews, we curate a final dataset of 158,065 annotated reviews. Of these, 89,371 are written entirely in Bangla. The remaining 68,694 reviews were written in Romanized Bangla, English, or a mix of languages. They are translated into Bangla with Google Translator and a custom Python program using the googletrans library. The translations are subsequently subjected to manual review and scrutiny to confirm their accuracy.

Results

Citation

If you find this work useful, please cite our paper:

@inproceedings{kabir-etal-2023-banglabook,
    title = "{B}angla{B}ook: A Large-scale {B}angla Dataset for Sentiment Analysis from Book Reviews",
    author = "Kabir, Mohsinul  and
      Bin Mahfuz, Obayed  and
      Raiyan, Syed Rifat  and
      Mahmud, Hasan  and
      Hasan, Md Kamrul",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-acl.80",
    pages = "1237--1247",
    abstract = "The analysis of consumer sentiment, as expressed through reviews, can provide a wealth of insight regarding the quality of a product. While the study of sentiment analysis has been widely explored in many popular languages, relatively less attention has been given to the Bangla language, mostly due to a lack of relevant data and cross-domain adaptability. To address this limitation, we present BanglaBook, a large-scale dataset of Bangla book reviews consisting of 158,065 samples classified into three broad categories: positive, negative, and neutral. We provide a detailed statistical analysis of the dataset and employ a range of machine learning models to establish baselines including SVM, LSTM, and Bangla-BERT. Our findings demonstrate a substantial performance advantage of pre-trained models over models that rely on manually crafted features, emphasizing the necessity for additional training resources in this domain. Additionally, we conduct an in-depth error analysis by examining sentiment unigrams, which may provide insight into common classification errors in under-resourced languages like Bangla. Our codes and data are publicly available at https://github.com/mohsinulkabir14/BanglaBook.",
}